← Back to Skills Marketplace
scnet-sugon

Bank Draft Ocr

by SCNet-sugon · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
53
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install bank-draft-ocr
Description
支持银行汇票识别,精准识别银行汇票票面信息,自动提取出票日期、收款人、付款行及票据金额等核心字段。。
README (SKILL.md)

\r

Sugon-Scnet 银行汇票识别 OCR 技能\r

\r 本技能封装了银行汇票识别的 OCR 服务,通过单一接口即可调用 1 种识别能力,精准识别银行汇票票面信息,自动提取出票日期、收款人、付款行及票据金额等核心字段。\r \r

功能特性\r

\r

  • 银行汇票识别:支持识别银行汇票信息,精准识别银行汇票票面信息,自动提取出票日期、收款人、付款行及票据金额等核心字段。\r \r \r \r

前置配置\r

\r

⚠️ 重要:使用前需要申请 Scnet API Token\r \r

申请 API Token\r

\r

  1. 访问 Scnet 官网 注册/登录\r
  2. 在控制台申请 API 密钥(格式:sc-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx)\r
  3. 复制密钥备用\r \r

配置 Token\r

\r 手动配置(推荐)\r

  1. 在技能目录下创建 config/.env 文件,内容如下:\r
# =====  Sugon-Scnet OCR API 配置 =====\r
# 申请地址:https://www.scnet.cn\r
SCNET_API_KEY=your_scnet_api_key_here\r
\r
# API 基础地址(一般无需修改)\r
SCNET_API_BASE=https://api.scnet.cn/api/llm/v1\r
```\r
2. 添加:`SCNET_API_KEY=你的密钥`\r
3. 设置文件权限为 600(仅所有者可读写)\r
**⚠️ 安全警告**:切勿将 API Key 直接粘贴到聊天对话中,否则可能被记录或泄露。\r
\r
### Token 更新\r
\r
Token 过期后调用会返回 401 或 403 错误。更新方法:重新申请 Token 并替换 config/.env 中的 SCNET_API_KEY。\r
\r
### 依赖安装\r
\r
本技能需要 Python 3.6+ 和 requests 库。请运行以下命令:\r
\r
```bash\r
   pip install requests\r
```\r
---\r
### 使用方法\r
\r
### 参数说明\r
\r
| 参数名 | 类型 | 必填 | 描述 |\r
|--------|------|------|------|\r
| ocrType | string | 是 | 识别类型枚举。必须为以下之一:\x3Cbr>• bank_draft_ocr(银行汇票)|\r
| filePath | string | 是 | 待识别图片的本地绝对路径。支持 jpg、png、pdf 等常见格式。 |\r
\r
### 命令行调用示例\r
\r
```bash\r
   python .claude/skills/bank_draft_ocr/scripts/main.py BANK_DRAFT /path/to/test.jpg\r
```\r
\r
### 在 AI 对话中使用\r
\r
用户可以说:\r
\r
- “帮我识别这张图像中的银行汇票信息,图片在 /Users/name/Downloads/test.jpg”\r
\r
AI 会根据 description 中的关键词自动触发本技能。\r
\r
### AI 调用建议\r
为避免触发 API 速率限制(10 QPS),请串行调用本技能,即等待前一个识别完成后再发起下一个请求。\r
如果使用 OpenClaw 的 exec 工具,建议设置 timeout 或 yieldMs 参数,让命令同步执行,避免多个命令同时运行导致并发。\r
\r
### 配置选项\r
\r
编辑 `config/.env` 文件:\r
\r
| 变量名 | 默认值 | 说明 |\r
|--------|--------|------|\r
| SCNET_API_KEY | 必需 | Scnet API 密钥 |\r
| SCNET_API_BASE | https://api.scnet.cn/api/llm/v1 | API 基础地址(一般无需修改) |\r
\r
### 输出\r
\r
- 标准输出:识别结果的 JSON 数据,结构与 API 文档一致,位于 `data` 字段内。\r
- 识别结果位于 data[0].result[0].elements 中,具体字段取决于 ocrType。\r
- 错误信息:如果发生错误,会输出以 `错误:` 开头的友好提示。\r
\r
### 注意事项\r
\r
- 本技能调用的 OCR API 有 10 QPS 的速率限制。\r
- 如果遇到 429 错误,请等待 2-3 秒后重试,不要连续发起请求。\r
- 建议在调用前确保图片已准备就绪,避免因网络问题导致重复调用。\r
\r
### 故障排除\r
\r
| 问题 | 解决方案 |\r
|------|----------|\r
| 配置文件不存在 | 创建 config/.env 并填入 Token(参考前置配置) |\r
| API Key 无效/过期 | 重新申请 Token 并更新 `.env` 文件 |\r
| 文件不存在 | 检查提供的文件路径是否正确 |\r
| 网络连接失败 | 检查网络连接或防火墙设置 |\r
| 不支持的文件类型 | 确保文件扩展名为允许的类型(参考 API 文档) |\r
| 401/403/Unauthorized | Token 无效或过期,重新申请并配置 |\r
| 429 Too Many Requests | 请求过于频繁,技能会自动等待并重试(最多 3 次)。若持续失败,请降低调用频率或联系服务方提高限额。 |\r
\r
\r
Usage Guidance
Install only if you are comfortable sending the selected bank draft image or PDF to Scnet for OCR. Avoid using it on documents you are not allowed to transmit to third parties, and do not paste API keys into chat; store the key locally as instructed.
Capability Tags
requires-sensitive-credentials
Capability Assessment
Purpose & Capability
The skill's stated purpose is bank draft OCR, and the script sends a user-provided file to the documented Scnet OCR endpoint and returns structured JSON; that behavior matches the purpose but inherently involves financial document data.
Instruction Scope
Runtime scope is limited to the configured API key, optional API base, and the single file path supplied by the user; there is no broad local scanning or hidden destination, though privacy and retention expectations are not documented clearly.
Install Mechanism
Installation is manual and minimal: Python plus requests, then a user-created config/.env for the SCNET_API_KEY. No automatic installer, package mutation, or background setup is present.
Credentials
Network upload of the selected image/PDF is proportionate for OCR, but bank drafts may contain account numbers, names, amounts, and other sensitive financial information.
Persistence & Privilege
The only persistence described is storing the Scnet API key in a local config/.env file with chmod 600 guidance; no privilege escalation, scheduled execution, or long-running worker is shown.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install bank-draft-ocr
  3. After installation, invoke the skill by name or use /bank-draft-ocr
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of bank_draft_ocr skill for precise bank draft (汇票) OCR recognition. - Supports automatic extraction of key fields: issue date, payee, remitting bank, and draft amount from images. - Requires SCNET_API_KEY for authentication; supports optional SCNET_API_BASE override. - Simple API: input image file path and select OCR type, returns structured JSON results including recognition details. - Includes detailed setup instructions, usage examples, error handling, and QPS limit guidance.
Metadata
Slug bank-draft-ocr
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Bank Draft Ocr?

支持银行汇票识别,精准识别银行汇票票面信息,自动提取出票日期、收款人、付款行及票据金额等核心字段。。 It is an AI Agent Skill for Claude Code / OpenClaw, with 53 downloads so far.

How do I install Bank Draft Ocr?

Run "/install bank-draft-ocr" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Bank Draft Ocr free?

Yes, Bank Draft Ocr is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Bank Draft Ocr support?

Bank Draft Ocr is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Bank Draft Ocr?

It is built and maintained by SCNet-sugon (@scnet-sugon); the current version is v1.0.0.

💬 Comments